Author used ChatGPT for architecture and the Junie agent in WebStorm to build a dashboard aggregating PRs across four repos, flagging approvals, conflicts and comments, in about 3 hours.
Author used ChatGPT for architecture and the Junie agent in WebStorm to build a dashboard aggregating PRs across four repos, flagging approvals, conflicts and comments, in about 3 hours.
The author described the goals to ChatGPT 5 to get an architecture, then gave that output to the Junie agent in WebStorm to write a Readme and project guidelines. They built it step by step: layout, dummy data, Azure API calls, YouTrack integration, features. PATs stay local. They hand-edited no code but read it and suggested improvements.
After about 3 hours there were three views, and the team loved it. Another hour added their suggestions, and everyone uses it daily. Almost every step worked first try; Junie sometimes got repetitive or inconsistent.
Adding a step to maximize code reuse and centralize configuration fixed the repetition and inconsistency Junie produced. The author says it struggles on their large .NET Maui codebase.
Build a dashboard that pulls open pull requests from my [Azure DevOps/GitHub] repos [repo names] and shows for each one its approval status, merge conflicts, and unresolved comments. Start with a simple architecture proposal, then build it step by step. Finished means the dashboard runs locally against my real repos with read-only access. Don't push code or change any PRs.
Export the Descript transcript, let ChatGPT pick the five strongest moments, and get 10 platform-ready posts in a review doc within minutes.
Give it a keyword and get a brief built from the pages that rank today: headings, gaps, questions to answer and a target length.
Spot order-status questions in the support inbox, look up the order in Shopify and reply with live tracking and an honest ETA.